| gpt-4-0613 (few-shot, val) |
unknown |
100 |
8192 |
True |
597 ± 197 / 93 ± 33 |
1.05 |
64.94 ± 1.96 / 45.76 ± 3.31 |
59.97 ± 2.65 / 73.06 ± 1.77 |
71.56 ± 2.49 / 85.36 ± 1.29 |
56.43 ± 2.98 / 68.46 ± 1.64 |
66.76 ± 0.34 / 18.99 ± 0.52 |
94.93 ± 1.03 / 96.21 ± 0.77 |
93.98 ± 2.15 / 95.94 ± 1.44 |
81.64 ± 1.80 / 86.17 ± 1.34 |
0.0.0 |
0.0.0 |
0.0.0 |
12.9.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.1.2 |
| meta-llama/Meta-Llama-3-70B (few-shot, val) |
70554 |
128 |
8192 |
True |
312 ± 55 / 177 ± 51 |
1.42 |
63.62 ± 3.74 / 53.29 ± 3.38 |
60.19 ± 3.31 / 73.13 ± 2.17 |
50.07 ± 5.86 / 72.94 ± 4.16 |
60.97 ± 2.76 / 66.71 ± 2.27 |
67.33 ± 1.41 / 22.84 ± 1.49 |
83.94 ± 1.20 / 87.93 ± 0.88 |
78.83 ± 3.17 / 85.39 ± 2.14 |
60.69 ± 4.11 / 69.38 ± 3.63 |
12.7.0 |
12.6.1 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| gpt-3.5-turbo-0613 (few-shot, val) |
unknown |
100 |
4094 |
True |
921 ± 293 / 113 ± 37 |
1.51 |
61.31 ± 2.34 / 49.86 ± 2.18 |
52.52 ± 2.05 / 68.10 ± 1.35 |
57.63 ± 2.80 / 77.01 ± 1.83 |
57.03 ± 1.95 / 65.51 ± 1.48 |
66.38 ± 0.26 / 18.03 ± 0.27 |
81.95 ± 2.61 / 86.33 ± 2.03 |
77.66 ± 2.57 / 85.08 ± 1.77 |
62.21 ± 2.60 / 71.05 ± 2.09 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.6.1 |
10.0.1 |
10.0.1 |
12.9.0 |
| meta-llama/Meta-Llama-3-70B-Instruct (few-shot, val) |
70554 |
128 |
8192 |
True |
1,673 ± 583 / 275 ± 85 |
1.59 |
63.10 ± 2.12 / 55.10 ± 1.44 |
53.09 ± 3.85 / 68.18 ± 2.27 |
40.98 ± 4.46 / 69.10 ± 2.72 |
51.13 ± 1.89 / 63.12 ± 1.61 |
67.76 ± 0.99 / 23.19 ± 0.71 |
85.18 ± 1.92 / 88.91 ± 1.44 |
79.22 ± 2.40 / 85.70 ± 1.72 |
70.19 ± 2.71 / 77.54 ± 2.05 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| meta-llama/Llama-2-70b-hf (few-shot, val) |
68977 |
32 |
4096 |
True |
1,892 ± 650 / 318 ± 105 |
1.68 |
58.06 ± 2.48 / 50.10 ± 2.23 |
53.24 ± 4.04 / 67.81 ± 2.74 |
39.71 ± 4.96 / 65.90 ± 3.81 |
62.51 ± 1.48 / 67.47 ± 1.39 |
67.39 ± 1.23 / 23.85 ± 1.20 |
84.43 ± 1.72 / 88.28 ± 1.24 |
71.35 ± 2.55 / 80.47 ± 1.72 |
54.31 ± 2.56 / 65.20 ± 2.09 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| 152334H/miqu-1-70b-sf (few-shot, val) |
68977 |
32 |
32764 |
True |
2,126 ± 676 / 319 ± 104 |
1.69 |
56.96 ± 2.39 / 45.84 ± 1.75 |
55.11 ± 4.11 / 69.60 ± 2.69 |
42.64 ± 3.22 / 71.04 ± 1.56 |
54.58 ± 2.19 / 64.12 ± 1.41 |
66.80 ± 1.09 / 20.36 ± 1.51 |
83.94 ± 1.81 / 87.97 ± 1.38 |
73.32 ± 4.97 / 81.64 ± 3.48 |
60.52 ± 3.33 / 70.08 ± 2.52 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| mhenrichsen/danskgpt-chat-v2.1 (few-shot) |
unknown |
32 |
32768 |
True |
5,085 ± 998 / 1,306 ± 404 |
1.92 |
51.08 ± 1.60 / 35.83 ± 1.84 |
54.69 ± 0.99 / 69.50 ± 0.93 |
30.95 ± 1.48 / 62.15 ± 1.83 |
56.56 ± 0.76 / 64.32 ± 0.40 |
66.90 ± 0.23 / 20.90 ± 0.64 |
79.39 ± 1.11 / 84.29 ± 0.86 |
73.22 ± 1.83 / 81.91 ± 1.32 |
48.16 ± 1.14 / 60.83 ± 0.97 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
12.0.0 |
| timpal0l/sol (few-shot) |
10732 |
32 |
4096 |
False |
3,701 ± 876 / 771 ± 247 |
1.96 |
54.91 ± 1.53 / 36.29 ± 1.85 |
44.38 ± 2.83 / 57.19 ± 3.61 |
21.11 ± 3.23 / 45.43 ± 3.11 |
58.96 ± 1.71 / 65.85 ± 1.20 |
66.89 ± 0.89 / 22.65 ± 0.84 |
61.12 ± 1.49 / 70.29 ± 1.16 |
64.86 ± 2.64 / 76.05 ± 1.94 |
67.96 ± 1.07 / 75.68 ± 0.86 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| Nexusflow/Starling-LM-7B-beta (few-shot) |
7242 |
32 |
8192 |
False |
5,876 ± 1,021 / 1,677 ± 546 |
1.97 |
53.20 ± 1.97 / 32.89 ± 2.00 |
51.75 ± 1.18 / 67.38 ± 0.95 |
32.72 ± 1.79 / 62.53 ± 2.00 |
56.44 ± 0.99 / 65.36 ± 0.51 |
67.46 ± 0.76 / 23.35 ± 0.88 |
59.78 ± 1.61 / 69.68 ± 1.23 |
58.63 ± 2.54 / 71.72 ± 1.82 |
50.74 ± 1.16 / 62.79 ± 0.92 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
| upstage/SOLAR-10.7B-v1.0 (few-shot) |
10732 |
32 |
4096 |
True |
3,780 ± 906 / 799 ± 261 |
1.98 |
58.03 ± 2.18 / 38.25 ± 2.31 |
46.63 ± 2.35 / 59.02 ± 3.07 |
15.09 ± 3.06 / 40.04 ± 1.77 |
62.15 ± 0.63 / 67.21 ± 0.55 |
66.81 ± 1.08 / 22.82 ± 1.04 |
64.79 ± 1.37 / 73.46 ± 1.07 |
68.59 ± 2.23 / 78.59 ± 1.60 |
65.29 ± 0.94 / 73.54 ± 0.74 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
| RJuro/munin-neuralbeagle-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
2,493 ± 466 / 773 ± 243 |
2.06 |
51.44 ± 3.28 / 41.38 ± 2.79 |
54.91 ± 2.59 / 67.84 ± 2.53 |
22.77 ± 3.96 / 52.29 ± 3.81 |
56.51 ± 1.80 / 64.01 ± 1.12 |
68.06 ± 1.42 / 24.28 ± 1.31 |
74.24 ± 2.14 / 80.62 ± 1.61 |
70.86 ± 3.58 / 80.31 ± 2.53 |
41.49 ± 2.88 / 55.86 ± 2.17 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| mlabonne/NeuralBeagle14-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
2,549 ± 472 / 784 ± 245 |
2.14 |
53.02 ± 2.85 / 41.35 ± 3.42 |
51.29 ± 3.42 / 66.57 ± 2.46 |
19.73 ± 4.11 / 57.07 ± 3.09 |
51.69 ± 2.29 / 61.26 ± 1.32 |
67.33 ± 1.40 / 22.77 ± 1.39 |
65.38 ± 2.59 / 73.95 ± 1.84 |
62.78 ± 4.04 / 74.61 ± 2.90 |
39.07 ± 2.57 / 53.83 ± 2.06 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| RJuro/munin-neuralbeagle-SkoleGPTOpenOrca-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
3,008 ± 429 / 991 ± 323 |
2.18 |
50.83 ± 2.28 / 36.96 ± 2.58 |
43.41 ± 2.56 / 48.74 ± 2.83 |
19.72 ± 4.69 / 52.71 ± 5.26 |
57.87 ± 2.32 / 64.53 ± 1.73 |
66.77 ± 0.99 / 21.60 ± 0.91 |
72.92 ± 2.52 / 79.69 ± 1.88 |
68.11 ± 3.00 / 78.52 ± 2.22 |
40.62 ± 3.23 / 55.12 ± 2.44 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| merge-crew/da-sv-slerp (few-shot, val) |
7242 |
32 |
32768 |
True |
2,467 ± 469 / 762 ± 244 |
2.20 |
45.94 ± 3.62 / 35.68 ± 3.35 |
51.75 ± 4.52 / 62.28 ± 4.29 |
28.04 ± 3.83 / 58.31 ± 5.00 |
57.65 ± 1.66 / 62.03 ± 1.50 |
66.65 ± 1.28 / 21.98 ± 1.17 |
68.88 ± 2.98 / 76.64 ± 2.22 |
64.81 ± 3.96 / 75.78 ± 2.64 |
23.63 ± 2.25 / 42.03 ± 2.02 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| merge-crew/da-sv-task-arithmetic (few-shot, val) |
7242 |
32 |
32768 |
True |
2,500 ± 469 / 762 ± 238 |
2.20 |
46.06 ± 3.28 / 35.43 ± 3.06 |
51.51 ± 4.23 / 61.68 ± 4.43 |
27.68 ± 4.25 / 57.59 ± 5.15 |
57.78 ± 1.43 / 62.26 ± 1.36 |
66.62 ± 1.35 / 21.92 ± 1.28 |
68.64 ± 3.34 / 76.45 ± 2.52 |
66.17 ± 3.73 / 76.72 ± 2.55 |
23.95 ± 2.64 / 42.19 ± 2.42 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| birgermoell/BeagleCatMunin-Flashback-Bellman (few-shot, val) |
7242 |
32 |
32768 |
False |
2,890 ± 401 / 1,155 ± 348 |
2.21 |
50.40 ± 2.92 / 38.57 ± 2.82 |
52.30 ± 2.65 / 64.19 ± 2.60 |
21.30 ± 3.52 / 47.78 ± 4.14 |
58.17 ± 1.71 / 63.79 ± 1.42 |
66.25 ± 1.29 / 20.33 ± 1.14 |
65.32 ± 3.33 / 73.95 ± 2.50 |
64.76 ± 3.24 / 75.94 ± 2.37 |
33.70 ± 2.78 / 50.16 ± 2.01 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| birgermoell/Rapid-Cycling (few-shot, val) |
7242 |
32 |
32768 |
False |
2,346 ± 450 / 666 ± 249 |
2.21 |
49.99 ± 2.62 / 38.37 ± 3.04 |
51.25 ± 2.70 / 62.67 ± 2.82 |
20.66 ± 5.69 / 49.98 ± 4.94 |
56.82 ± 1.75 / 62.40 ± 1.40 |
65.58 ± 1.30 / 17.82 ± 1.12 |
67.48 ± 3.13 / 75.62 ± 2.33 |
63.69 ± 2.43 / 75.31 ± 1.76 |
32.11 ± 3.47 / 48.55 ± 2.67 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| timpal0l/BeagleCatMunin2 (few-shot, val) |
7242 |
32 |
32768 |
False |
2,477 ± 459 / 767 ± 241 |
2.21 |
51.53 ± 2.82 / 40.66 ± 2.30 |
47.95 ± 3.02 / 55.70 ± 3.32 |
14.10 ± 3.79 / 40.80 ± 3.64 |
58.28 ± 1.98 / 64.33 ± 1.60 |
68.04 ± 1.34 / 24.72 ± 1.42 |
67.37 ± 4.12 / 75.55 ± 3.01 |
66.75 ± 3.42 / 77.34 ± 2.58 |
42.21 ± 3.40 / 56.48 ± 2.62 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| meta-llama/Llama-2-70b-chat-hf (few-shot, val) |
68977 |
32 |
4096 |
True |
1,979 ± 621 / 320 ± 105 |
2.23 |
52.22 ± 2.07 / 38.82 ± 1.90 |
50.66 ± 1.88 / 62.04 ± 2.83 |
23.57 ± 3.82 / 56.09 ± 4.62 |
53.82 ± 2.13 / 61.94 ± 1.63 |
67.13 ± 0.72 / 21.62 ± 0.86 |
69.26 ± 2.89 / 76.99 ± 2.16 |
46.40 ± 2.92 / 59.45 ± 2.63 |
39.72 ± 2.48 / 53.83 ± 2.19 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| timpal0l/BeagleCatMunin (few-shot, val) |
7242 |
32 |
32768 |
False |
2,495 ± 458 / 775 ± 244 |
2.25 |
47.62 ± 3.01 / 36.77 ± 2.96 |
54.73 ± 3.20 / 68.74 ± 2.21 |
21.80 ± 4.54 / 51.07 ± 4.11 |
57.26 ± 1.76 / 63.60 ± 1.40 |
67.31 ± 1.40 / 23.24 ± 1.64 |
66.49 ± 2.90 / 74.84 ± 2.12 |
60.41 ± 1.95 / 72.97 ± 1.45 |
28.51 ± 3.95 / 45.74 ± 3.03 |
9.3.2 |
9.3.2 |
9.3.2 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| Mabeck/Heidrun-Mistral-7B-chat (few-shot) |
7242 |
32 |
32768 |
False |
5,822 ± 1,283 / 1,336 ± 430 |
2.30 |
50.80 ± 2.33 / 34.04 ± 1.76 |
42.79 ± 2.38 / 54.47 ± 3.04 |
23.25 ± 3.17 / 56.31 ± 4.02 |
59.90 ± 0.84 / 65.47 ± 0.43 |
67.50 ± 0.95 / 23.95 ± 0.59 |
66.61 ± 0.93 / 74.86 ± 0.71 |
64.80 ± 1.46 / 76.46 ± 1.02 |
29.18 ± 0.99 / 46.64 ± 0.76 |
10.0.1 |
10.0.1 |
10.0.1 |
12.5.0 |
12.6.1 |
10.0.1 |
11.0.0 |
10.0.1 |
| four-two-labs/orpo-llama-3-swe (few-shot) |
8030 |
128 |
8192 |
False |
4,974 ± 1,208 / 1,032 ± 342 |
2.30 |
46.75 ± 2.79 / 29.40 ± 2.22 |
51.73 ± 1.40 / 66.43 ± 1.93 |
24.73 ± 4.78 / 53.98 ± 6.10 |
59.97 ± 1.27 / 65.74 ± 0.76 |
65.21 ± 0.51 / 18.86 ± 0.87 |
55.72 ± 2.05 / 66.59 ± 1.56 |
61.59 ± 2.64 / 73.95 ± 1.89 |
25.43 ± 2.44 / 43.11 ± 2.03 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| meta-llama/Meta-Llama-3-8B (few-shot) |
8030 |
128 |
8192 |
True |
4,687 ± 1,121 / 967 ± 313 |
2.30 |
46.31 ± 3.22 / 29.09 ± 2.52 |
51.29 ± 1.47 / 66.35 ± 1.70 |
25.70 ± 4.59 / 55.65 ± 5.87 |
59.79 ± 1.21 / 65.44 ± 0.76 |
65.16 ± 0.48 / 18.74 ± 0.83 |
56.20 ± 2.22 / 66.91 ± 1.68 |
61.16 ± 2.54 / 73.63 ± 1.85 |
24.99 ± 2.12 / 42.57 ± 1.91 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
| senseable/WestLake-7B-v2 (few-shot) |
7242 |
32 |
32768 |
False |
5,993 ± 1,028 / 1,742 ± 561 |
2.30 |
52.61 ± 1.77 / 33.64 ± 2.67 |
49.81 ± 1.43 / 66.32 ± 1.25 |
19.64 ± 1.63 / 54.22 ± 2.32 |
48.03 ± 1.24 / 57.94 ± 1.02 |
66.67 ± 0.87 / 21.08 ± 0.83 |
57.65 ± 1.99 / 68.08 ± 1.51 |
51.99 ± 3.67 / 66.43 ± 2.85 |
44.44 ± 1.52 / 58.16 ± 1.21 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
| syvai/llama3-da-base (few-shot) |
8030 |
128 |
8192 |
True |
3,191 ± 1,053 / 446 ± 147 |
2.30 |
49.97 ± 3.05 / 34.87 ± 3.11 |
48.61 ± 1.35 / 60.53 ± 2.13 |
28.16 ± 3.02 / 59.87 ± 3.44 |
59.55 ± 1.23 / 65.50 ± 0.77 |
66.16 ± 0.83 / 20.83 ± 1.23 |
54.55 ± 2.11 / 65.21 ± 1.63 |
62.19 ± 2.34 / 74.20 ± 1.57 |
20.36 ± 2.18 / 38.27 ± 2.03 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
| timpal0l/dolphin-2.9-llama3-8b-flashback (few-shot, val) |
8030 |
128 |
8192 |
False |
5,018 ± 1,216 / 996 ± 324 |
2.30 |
51.37 ± 2.38 / 37.56 ± 2.50 |
52.17 ± 3.44 / 67.14 ± 2.61 |
27.98 ± 7.51 / 60.57 ± 5.72 |
51.65 ± 0.84 / 59.94 ± 0.78 |
66.25 ± 1.15 / 19.93 ± 1.18 |
57.31 ± 2.81 / 68.05 ± 2.05 |
54.17 ± 2.95 / 68.20 ± 1.83 |
27.65 ± 3.28 / 44.53 ± 2.63 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| danish-foundation-models/munin-7b-v0.1dev0 (few-shot) |
7242 |
32 |
8192 |
True |
6,113 ± 1,044 / 1,790 ± 579 |
2.32 |
39.12 ± 4.28 / 28.74 ± 2.75 |
36.47 ± 4.90 / 50.72 ± 6.21 |
26.76 ± 4.78 / 57.02 ± 5.13 |
58.75 ± 1.19 / 64.41 ± 0.77 |
67.89 ± 1.20 / 24.67 ± 1.26 |
91.32 ± 0.66 / 93.45 ± 0.50 |
79.92 ± 1.83 / 85.82 ± 1.39 |
24.76 ± 3.27 / 42.17 ± 2.72 |
12.5.2 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
12.4.0 |
| mlabonne/AlphaMonarch-7B (few-shot, val) |
7242 |
32 |
8192 |
False |
5,340 ± 1,262 / 1,157 ± 375 |
2.33 |
52.72 ± 2.21 / 39.49 ± 3.47 |
49.11 ± 3.91 / 64.78 ± 2.61 |
16.09 ± 3.74 / 54.94 ± 2.92 |
46.28 ± 1.53 / 56.13 ± 1.09 |
66.62 ± 0.96 / 21.03 ± 0.80 |
60.03 ± 5.14 / 70.04 ± 3.73 |
59.83 ± 4.38 / 72.27 ± 3.40 |
40.40 ± 3.24 / 55.04 ± 2.57 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.6.1 |
12.5.2 |
12.5.2 |
12.5.2 |
| ThatsGroes/munin-SkoleGPTOpenOrca-7b-16bit (few-shot) |
7242 |
32 |
32768 |
False |
3,006 ± 479 / 1,053 ± 319 |
2.34 |
45.37 ± 2.53 / 28.99 ± 2.18 |
39.63 ± 1.90 / 46.93 ± 2.68 |
21.77 ± 3.54 / 47.96 ± 4.57 |
58.28 ± 0.73 / 64.76 ± 0.47 |
67.91 ± 0.79 / 24.44 ± 0.46 |
78.71 ± 1.22 / 83.82 ± 0.94 |
63.74 ± 2.06 / 74.88 ± 1.46 |
28.58 ± 0.96 / 45.97 ± 0.76 |
11.0.0 |
11.0.0 |
11.0.0 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
11.0.0 |
| meta-llama/Meta-Llama-3-8B-Instruct (few-shot) |
8030 |
128 |
8192 |
True |
4,909 ± 1,215 / 978 ± 319 |
2.35 |
57.74 ± 2.06 / 40.66 ± 2.58 |
48.43 ± 3.31 / 62.09 ± 3.62 |
27.12 ± 2.83 / 60.40 ± 2.70 |
46.76 ± 1.20 / 59.77 ± 0.51 |
66.36 ± 0.47 / 19.75 ± 0.84 |
57.87 ± 1.67 / 67.43 ± 1.34 |
50.42 ± 3.32 / 65.43 ± 2.41 |
29.17 ± 2.24 / 44.59 ± 2.00 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
| timpal0l/njord-alpha (few-shot) |
7242 |
32 |
32768 |
True |
5,431 ± 1,267 / 1,139 ± 365 |
2.35 |
38.25 ± 3.75 / 28.14 ± 3.06 |
39.37 ± 2.09 / 56.57 ± 1.90 |
29.76 ± 3.24 / 61.80 ± 2.22 |
57.02 ± 1.28 / 63.16 ± 0.90 |
67.57 ± 1.27 / 24.15 ± 1.17 |
83.45 ± 1.44 / 87.17 ± 1.20 |
70.43 ± 2.76 / 79.43 ± 1.95 |
16.43 ± 1.75 / 33.75 ± 1.91 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| birgermoell/Munin-NeuralBeagle-NorskGPT (few-shot, val) |
7242 |
32 |
32768 |
False |
2,903 ± 407 / 1,157 ± 350 |
2.37 |
51.85 ± 3.08 / 40.02 ± 2.48 |
44.02 ± 2.44 / 47.74 ± 1.98 |
1.22 ± 4.99 / 34.29 ± 1.62 |
57.69 ± 2.29 / 64.09 ± 1.68 |
67.69 ± 1.19 / 23.90 ± 1.25 |
68.45 ± 3.11 / 76.37 ± 2.29 |
65.51 ± 3.45 / 76.56 ± 2.62 |
42.09 ± 3.27 / 56.33 ± 2.56 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| birgermoell/WestLake-Munin-Cat-NorskGPT (few-shot, val) |
7242 |
32 |
32768 |
False |
2,856 ± 391 / 1,142 ± 342 |
2.37 |
51.85 ± 3.08 / 40.02 ± 2.48 |
44.02 ± 2.44 / 47.74 ± 1.98 |
1.22 ± 4.99 / 34.29 ± 1.62 |
57.69 ± 2.29 / 64.09 ± 1.68 |
67.69 ± 1.19 / 23.88 ± 1.23 |
68.45 ± 3.11 / 76.37 ± 2.29 |
65.51 ± 3.45 / 76.56 ± 2.62 |
42.09 ± 3.27 / 56.33 ± 2.56 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| birgermoell/Flashback-Bellman (few-shot, val) |
7242 |
32 |
32768 |
False |
2,887 ± 403 / 1,144 ± 345 |
2.39 |
47.71 ± 3.50 / 35.65 ± 3.07 |
48.21 ± 3.58 / 60.08 ± 3.41 |
19.55 ± 5.35 / 50.98 ± 5.74 |
56.46 ± 1.48 / 61.69 ± 1.28 |
65.46 ± 1.23 / 17.73 ± 1.16 |
61.29 ± 2.33 / 70.82 ± 1.78 |
60.29 ± 2.58 / 72.97 ± 1.79 |
28.33 ± 2.11 / 45.86 ± 1.72 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| bineric/NorskGPT-Llama3-8b (few-shot) |
8030 |
128 |
8192 |
False |
3,695 ± 1,277 / 532 ± 183 |
2.40 |
51.40 ± 3.08 / 37.70 ± 3.28 |
42.13 ± 0.57 / 45.91 ± 0.39 |
3.91 ± 2.02 / 34.38 ± 0.47 |
57.81 ± 1.03 / 66.28 ± 0.48 |
66.70 ± 0.98 / 21.56 ± 0.85 |
65.15 ± 1.40 / 73.55 ± 1.05 |
57.36 ± 2.49 / 70.88 ± 1.70 |
44.55 ± 1.98 / 57.29 ± 1.77 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| birgermoell/NeuralBeagle-Flashback (few-shot, val) |
7242 |
32 |
32768 |
False |
2,904 ± 405 / 1,155 ± 349 |
2.40 |
48.28 ± 2.73 / 36.42 ± 3.04 |
44.20 ± 2.63 / 53.54 ± 3.36 |
22.79 ± 5.54 / 54.63 ± 6.09 |
57.96 ± 0.80 / 63.50 ± 0.73 |
65.62 ± 1.30 / 17.98 ± 1.11 |
62.80 ± 2.47 / 72.15 ± 1.80 |
61.54 ± 2.29 / 73.98 ± 1.58 |
25.54 ± 2.80 / 43.01 ± 1.95 |
9.3.0 |
9.3.0 |
9.3.0 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.0 |
| danish-foundation-models/munin-7b-alpha (few-shot) |
7242 |
32 |
32768 |
True |
6,116 ± 1,049 / 1,784 ± 577 |
2.40 |
40.60 ± 2.25 / 28.71 ± 1.42 |
36.89 ± 2.27 / 43.77 ± 2.64 |
26.41 ± 5.40 / 53.03 ± 6.56 |
57.81 ± 1.11 / 63.44 ± 0.81 |
67.27 ± 1.15 / 23.82 ± 0.97 |
77.63 ± 1.33 / 83.01 ± 1.00 |
67.83 ± 1.25 / 77.91 ± 0.89 |
25.16 ± 2.44 / 42.68 ± 2.10 |
12.5.2 |
12.4.0 |
12.4.0 |
12.4.0 |
12.6.1 |
12.4.0 |
12.4.0 |
12.4.0 |
| AI-Sweden-Models/tyr (few-shot, val) |
7242 |
32 |
32768 |
False |
6,079 ± 1,051 / 1,760 ± 570 |
2.42 |
47.01 ± 2.76 / 36.47 ± 3.27 |
50.60 ± 3.33 / 65.49 ± 2.38 |
13.73 ± 3.33 / 52.15 ± 3.17 |
56.35 ± 1.68 / 61.63 ± 1.33 |
66.82 ± 1.02 / 22.26 ± 1.10 |
57.53 ± 3.61 / 67.77 ± 2.64 |
67.04 ± 2.33 / 78.12 ± 1.58 |
22.16 ± 1.56 / 40.90 ± 1.34 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.3.2 |
| merge-crew/da-sv-dare-ties-density-0.9 (few-shot, val) |
7242 |
32 |
32768 |
True |
2,443 ± 458 / 750 ± 240 |
2.43 |
45.61 ± 3.06 / 35.04 ± 2.94 |
53.73 ± 3.06 / 67.51 ± 2.16 |
17.08 ± 5.36 / 52.62 ± 5.62 |
56.67 ± 1.19 / 61.18 ± 1.07 |
66.14 ± 1.40 / 20.98 ± 1.16 |
60.58 ± 2.62 / 69.80 ± 2.03 |
57.89 ± 3.66 / 70.00 ± 2.59 |
16.45 ± 1.87 / 35.47 ± 1.77 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| KennethEnevoldsen/munin_mistral-7b (few-shot, val) |
7242 |
32 |
32768 |
False |
2,543 ± 466 / 787 ± 247 |
2.44 |
46.70 ± 3.49 / 36.30 ± 2.65 |
47.52 ± 3.90 / 55.98 ± 4.69 |
8.04 ± 5.32 / 36.02 ± 2.59 |
60.05 ± 1.30 / 64.15 ± 1.20 |
67.18 ± 1.23 / 22.71 ± 1.10 |
70.49 ± 3.13 / 77.89 ± 2.32 |
66.28 ± 4.60 / 76.88 ± 3.34 |
25.13 ± 3.45 / 43.24 ± 2.58 |
12.5.2 |
12.3.1 |
12.3.1 |
12.3.2 |
12.6.1 |
12.3.2 |
12.3.2 |
12.3.2 |
| merge-crew/da-sv-ties (few-shot, val) |
7242 |
32 |
32768 |
True |
2,457 ± 451 / 757 ± 237 |
2.46 |
45.39 ± 2.46 / 34.45 ± 2.56 |
51.95 ± 2.65 / 65.69 ± 2.11 |
13.25 ± 6.27 / 45.66 ± 5.58 |
58.51 ± 1.35 / 62.73 ± 1.19 |
66.33 ± 1.33 / 21.24 ± 1.23 |
57.16 ± 3.03 / 66.99 ± 2.44 |
60.06 ± 3.26 / 71.17 ± 2.36 |
13.62 ± 3.14 / 33.40 ± 2.67 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| timpal0l/Llama-3-8B-flashback-v1 (few-shot) |
8030 |
128 |
8192 |
True |
4,849 ± 1,171 / 974 ± 316 |
2.48 |
42.71 ± 4.20 / 28.63 ± 2.95 |
51.24 ± 1.78 / 66.81 ± 1.62 |
19.78 ± 2.85 / 54.81 ± 4.38 |
56.28 ± 1.82 / 62.13 ± 1.35 |
64.25 ± 0.95 / 17.80 ± 1.04 |
49.36 ± 1.28 / 61.48 ± 0.97 |
55.56 ± 1.62 / 70.21 ± 1.19 |
20.27 ± 2.42 / 39.50 ± 2.01 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| bineric/NorskGPT-Mistral-7b (few-shot) |
7242 |
32 |
32768 |
False |
2,443 ± 451 / 761 ± 237 |
2.50 |
50.76 ± 1.60 / 32.89 ± 2.11 |
40.41 ± 0.79 / 44.17 ± 0.56 |
0.00 ± 0.00 / 33.41 ± 0.23 |
57.26 ± 0.79 / 63.80 ± 0.52 |
66.89 ± 0.71 / 21.43 ± 0.57 |
64.32 ± 1.99 / 73.00 ± 1.51 |
53.18 ± 2.37 / 67.48 ± 1.70 |
43.42 ± 1.05 / 57.50 ± 0.80 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| Mabeck/Heidrun-Mistral-7B-base (few-shot) |
7242 |
32 |
32768 |
True |
3,823 ± 967 / 860 ± 280 |
2.52 |
40.14 ± 2.41 / 28.08 ± 1.67 |
39.38 ± 1.56 / 49.16 ± 2.84 |
21.85 ± 3.24 / 53.75 ± 4.63 |
58.07 ± 1.13 / 63.63 ± 0.69 |
67.06 ± 1.05 / 23.60 ± 0.84 |
60.78 ± 1.64 / 69.96 ± 1.28 |
61.29 ± 2.78 / 73.50 ± 1.95 |
16.26 ± 1.96 / 35.70 ± 1.73 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
| alpindale/Mistral-7B-v0.2-hf (few-shot) |
7242 |
32 |
32768 |
True |
1,841 ± 297 / 651 ± 193 |
2.55 |
43.65 ± 2.87 / 32.21 ± 2.13 |
45.86 ± 1.63 / 61.89 ± 1.57 |
15.19 ± 3.67 / 46.19 ± 5.60 |
59.14 ± 0.90 / 64.43 ± 0.58 |
66.30 ± 1.02 / 21.99 ± 1.01 |
53.67 ± 1.74 / 64.67 ± 1.45 |
54.52 ± 2.51 / 68.59 ± 1.76 |
20.51 ± 2.03 / 39.10 ± 1.86 |
12.5.2 |
12.5.1 |
12.5.1 |
12.5.1 |
12.6.1 |
12.5.1 |
12.5.1 |
12.5.1 |
| merge-crew/da-sv-dare-ties-density-0.6 (few-shot, val) |
7242 |
32 |
32768 |
True |
2,515 ± 465 / 785 ± 247 |
2.56 |
46.03 ± 3.93 / 34.23 ± 2.86 |
49.59 ± 3.26 / 63.45 ± 2.61 |
12.72 ± 3.51 / 46.56 ± 5.33 |
57.03 ± 1.13 / 61.58 ± 1.01 |
65.24 ± 1.45 / 19.37 ± 1.48 |
59.88 ± 2.64 / 69.41 ± 2.10 |
59.51 ± 3.33 / 71.02 ± 2.26 |
16.86 ± 4.05 / 34.77 ± 3.07 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| mistralai/Mistral-7B-Instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
2,538 ± 415 / 821 ± 253 |
2.59 |
44.89 ± 2.46 / 29.13 ± 1.92 |
48.09 ± 1.00 / 65.40 ± 0.75 |
19.06 ± 2.34 / 58.77 ± 1.37 |
51.56 ± 1.16 / 60.81 ± 0.74 |
66.84 ± 0.77 / 21.21 ± 1.08 |
51.60 ± 1.33 / 63.50 ± 1.03 |
35.85 ± 2.68 / 52.62 ± 2.08 |
22.21 ± 1.60 / 40.78 ± 1.32 |
9.2.0 |
9.2.0 |
9.3.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| timpal0l/Mistral-7B-v0.1-flashback-v2 (few-shot) |
7242 |
32 |
32768 |
True |
5,054 ± 1,200 / 1,056 ± 339 |
2.62 |
42.43 ± 3.36 / 29.30 ± 2.53 |
47.82 ± 2.00 / 63.19 ± 2.09 |
16.51 ± 2.59 / 52.73 ± 3.91 |
56.95 ± 1.21 / 62.20 ± 0.83 |
65.43 ± 1.12 / 20.36 ± 0.95 |
50.76 ± 1.75 / 62.66 ± 1.43 |
50.82 ± 1.17 / 66.66 ± 0.76 |
14.47 ± 2.35 / 34.86 ± 1.97 |
12.5.3 |
12.5.3 |
12.5.3 |
12.5.3 |
12.6.1 |
12.5.3 |
12.5.3 |
12.5.3 |
| mhenrichsen/hestenettetLM (few-shot) |
7242 |
32 |
32768 |
True |
5,160 ± 804 / 1,654 ± 516 |
2.63 |
44.90 ± 3.15 / 31.91 ± 2.65 |
42.61 ± 1.79 / 53.47 ± 3.00 |
8.65 ± 3.44 / 38.18 ± 4.21 |
59.62 ± 1.12 / 64.70 ± 0.75 |
66.48 ± 0.99 / 22.13 ± 1.09 |
52.83 ± 1.98 / 64.27 ± 1.66 |
57.96 ± 2.76 / 71.31 ± 1.89 |
18.11 ± 3.15 / 37.65 ± 2.44 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.6.1 |
12.3.2 |
12.3.2 |
12.3.2 |
| mistralai/Mistral-7B-v0.1 (few-shot) |
7242 |
32 |
32768 |
True |
2,657 ± 524 / 880 ± 278 |
2.63 |
45.42 ± 2.88 / 32.66 ± 2.49 |
43.16 ± 1.69 / 54.53 ± 2.83 |
8.79 ± 3.23 / 38.38 ± 4.22 |
59.43 ± 1.04 / 64.55 ± 0.68 |
66.47 ± 1.00 / 22.11 ± 1.08 |
53.26 ± 1.94 / 64.50 ± 1.68 |
58.26 ± 2.62 / 71.56 ± 1.79 |
18.53 ± 2.03 / 37.79 ± 1.68 |
0.0.0 |
0.0.0 |
0.0.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.1.2 |
| RuterNorway/Llama-2-13b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
3,254 ± 1,068 / 484 ± 173 |
2.66 |
43.17 ± 2.78 / 31.37 ± 2.95 |
43.40 ± 2.20 / 57.24 ± 3.52 |
11.08 ± 2.98 / 43.40 ± 4.66 |
56.81 ± 0.70 / 63.10 ± 0.35 |
67.46 ± 0.28 / 22.85 ± 0.60 |
52.94 ± 1.40 / 64.04 ± 1.18 |
41.65 ± 1.43 / 59.92 ± 0.88 |
17.57 ± 1.83 / 37.68 ± 1.55 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
9.3.1 |
11.0.0 |
11.0.0 |
9.3.1 |
| neph1/bellman-7b-mistral-instruct-v0.2 (few-shot) |
7242 |
32 |
32768 |
False |
2,518 ± 463 / 779 ± 243 |
2.67 |
46.11 ± 3.27 / 28.75 ± 2.13 |
47.58 ± 1.41 / 63.81 ± 1.28 |
18.41 ± 2.11 / 57.44 ± 2.11 |
52.78 ± 1.15 / 60.80 ± 0.59 |
65.65 ± 0.82 / 18.78 ± 0.80 |
41.77 ± 1.71 / 55.65 ± 1.27 |
35.86 ± 2.28 / 52.48 ± 1.70 |
11.59 ± 1.75 / 32.81 ± 1.55 |
9.2.0 |
9.2.0 |
9.2.0 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.2.0 |
| mistralai/Mistral-7B-Instruct-v0.1 (few-shot) |
7242 |
32 |
32768 |
False |
5,443 ± 1,273 / 1,144 ± 364 |
2.80 |
37.93 ± 2.71 / 23.54 ± 1.99 |
44.49 ± 2.56 / 60.64 ± 3.00 |
14.09 ± 2.94 / 42.43 ± 3.30 |
51.38 ± 2.31 / 58.78 ± 1.27 |
65.80 ± 0.93 / 19.91 ± 1.41 |
45.07 ± 1.34 / 58.18 ± 1.03 |
35.36 ± 2.19 / 55.82 ± 1.48 |
14.85 ± 1.19 / 35.26 ± 1.24 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| occiglot/occiglot-7b-eu5-instruct (few-shot) |
7242 |
32 |
32768 |
False |
2,088 ± 352 / 706 ± 214 |
2.80 |
40.19 ± 2.55 / 29.73 ± 1.44 |
42.31 ± 1.55 / 59.29 ± 2.00 |
1.14 ± 1.22 / 33.83 ± 0.72 |
57.89 ± 1.16 / 63.95 ± 0.82 |
66.68 ± 0.81 / 22.38 ± 0.71 |
44.30 ± 2.46 / 57.00 ± 2.30 |
48.76 ± 2.39 / 65.51 ± 1.72 |
15.44 ± 1.66 / 35.82 ± 1.14 |
12.5.2 |
12.2.0 |
12.3.1 |
12.4.0 |
12.6.1 |
12.3.1 |
12.3.1 |
12.3.1 |
| bineric/NorskGPT-Llama-7B-v0.1 (few-shot) |
6738 |
32 |
4096 |
False |
5,384 ± 879 / 1,746 ± 553 |
2.82 |
41.63 ± 2.33 / 28.51 ± 2.43 |
47.73 ± 1.52 / 60.64 ± 2.33 |
0.00 ± 0.00 / 33.41 ± 0.23 |
54.25 ± 0.85 / 61.70 ± 0.71 |
66.02 ± 0.52 / 19.78 ± 0.57 |
47.16 ± 1.82 / 59.60 ± 1.51 |
38.28 ± 1.21 / 58.13 ± 0.76 |
22.27 ± 1.19 / 41.07 ± 1.07 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.6.1 |
12.3.2 |
12.3.2 |
12.3.2 |
| meta-llama/Llama-2-7b-chat-hf (few-shot) |
6738 |
32 |
4096 |
False |
2,643 ± 455 / 800 ± 247 |
2.90 |
35.44 ± 3.00 / 24.63 ± 1.65 |
44.88 ± 1.45 / 62.35 ± 1.33 |
9.74 ± 1.96 / 47.42 ± 4.19 |
55.04 ± 0.79 / 61.34 ± 0.81 |
66.15 ± 0.67 / 19.69 ± 0.94 |
32.17 ± 2.28 / 46.67 ± 1.92 |
35.74 ± 2.46 / 55.18 ± 1.81 |
11.32 ± 0.41 / 32.24 ± 0.79 |
9.3.1 |
9.3.1 |
9.3.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| occiglot/occiglot-7b-eu5 (few-shot) |
7242 |
32 |
32768 |
True |
2,219 ± 427 / 717 ± 224 |
2.91 |
37.93 ± 3.09 / 29.50 ± 2.18 |
44.62 ± 1.98 / 62.62 ± 1.54 |
0.28 ± 0.54 / 33.48 ± 0.24 |
58.05 ± 1.02 / 62.89 ± 0.89 |
66.05 ± 1.13 / 21.82 ± 0.96 |
38.54 ± 1.47 / 53.57 ± 1.26 |
45.89 ± 3.00 / 63.14 ± 1.98 |
12.38 ± 1.99 / 33.54 ± 1.61 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.2.0 |
| google/gemma-7b-it (few-shot) |
8538 |
256 |
8192 |
False |
1,792 ± 249 / 668 ± 203 |
2.95 |
43.83 ± 1.93 / 34.03 ± 1.59 |
29.21 ± 1.92 / 52.86 ± 1.54 |
12.96 ± 1.67 / 55.83 ± 0.88 |
49.76 ± 0.59 / 56.52 ± 0.50 |
65.36 ± 1.08 / 19.65 ± 1.01 |
41.30 ± 1.79 / 54.09 ± 1.68 |
31.26 ± 2.75 / 52.68 ± 2.10 |
15.02 ± 1.01 / 34.38 ± 0.79 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
| merge-crew/da-sv-dare-ties-density-0.3 (few-shot, val) |
7242 |
32 |
32768 |
True |
2,461 ± 476 / 773 ± 248 |
2.95 |
30.16 ± 4.47 / 25.03 ± 3.01 |
48.49 ± 2.41 / 63.06 ± 1.91 |
5.52 ± 4.66 / 38.81 ± 4.27 |
52.44 ± 1.32 / 57.22 ± 1.44 |
64.24 ± 1.42 / 18.43 ± 1.20 |
43.57 ± 3.32 / 56.56 ± 2.69 |
35.60 ± 4.28 / 50.86 ± 3.49 |
6.76 ± 2.77 / 28.91 ± 2.38 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| timpal0l/Mistral-7B-v0.1-flashback-v2-instruct (few-shot) |
7242 |
32 |
32768 |
False |
5,172 ± 813 / 1,647 ± 518 |
2.95 |
37.02 ± 5.66 / 27.64 ± 3.92 |
40.65 ± 2.10 / 57.47 ± 2.56 |
7.48 ± 2.51 / 46.56 ± 4.52 |
52.71 ± 0.70 / 59.07 ± 0.65 |
64.46 ± 0.75 / 14.29 ± 0.40 |
47.26 ± 2.07 / 60.38 ± 1.55 |
49.54 ± 1.64 / 66.15 ± 1.06 |
9.02 ± 1.22 / 30.79 ± 0.64 |
12.5.2 |
12.3.2 |
12.3.2 |
12.4.0 |
12.6.1 |
12.3.2 |
12.3.2 |
12.3.2 |
| Qwen/Qwen1.5-4B-Chat (few-shot) |
3950 |
152 |
32768 |
False |
4,347 ± 893 / 1,135 ± 365 |
2.96 |
35.96 ± 2.61 / 28.58 ± 2.58 |
42.04 ± 1.42 / 60.76 ± 1.41 |
8.65 ± 1.52 / 49.56 ± 3.60 |
53.68 ± 0.94 / 59.73 ± 0.86 |
63.22 ± 1.14 / 16.73 ± 1.50 |
37.79 ± 1.24 / 52.64 ± 0.99 |
29.62 ± 1.33 / 52.29 ± 1.02 |
16.87 ± 1.18 / 37.41 ± 0.90 |
12.5.2 |
10.0.1 |
12.1.0 |
12.5.2 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| meta-llama/Llama-2-7b-hf (few-shot) |
6738 |
32 |
4096 |
True |
930 ± 310 / 128 ± 43 |
3.04 |
31.77 ± 3.29 / 22.31 ± 2.29 |
43.91 ± 1.94 / 61.54 ± 2.33 |
0.31 ± 0.61 / 33.43 ± 0.23 |
58.44 ± 0.83 / 63.54 ± 0.66 |
65.50 ± 0.82 / 19.96 ± 0.95 |
20.18 ± 1.80 / 38.69 ± 1.57 |
35.69 ± 2.31 / 57.05 ± 1.60 |
7.93 ± 1.49 / 29.76 ± 0.92 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.2.0 |
| tollefj/nordavind-7b-instruct-warm (few-shot) |
7248 |
33 |
2048 |
False |
6,450 ± 961 / 2,082 ± 658 |
3.05 |
38.39 ± 3.57 / 24.87 ± 2.52 |
49.44 ± 1.03 / 66.00 ± 0.88 |
7.50 ± 2.07 / 47.53 ± 4.03 |
51.24 ± 1.09 / 57.72 ± 0.98 |
66.09 ± 1.40 / 22.03 ± 1.26 |
3.53 ± 1.44 / 24.18 ± 1.19 |
12.86 ± 2.99 / 40.23 ± 2.31 |
1.29 ± 1.23 / 25.61 ± 0.84 |
12.5.2 |
12.3.2 |
12.3.2 |
12.4.0 |
12.6.1 |
12.3.2 |
12.3.2 |
12.3.2 |
| Qwen/Qwen1.5-4B (few-shot) |
3950 |
152 |
32768 |
True |
3,248 ± 739 / 761 ± 252 |
3.07 |
32.28 ± 3.16 / 23.24 ± 3.51 |
39.62 ± 2.39 / 56.09 ± 2.89 |
5.38 ± 2.18 / 36.31 ± 1.96 |
54.16 ± 0.89 / 60.63 ± 0.75 |
62.74 ± 1.62 / 16.48 ± 1.77 |
37.49 ± 1.84 / 51.62 ± 1.43 |
29.21 ± 3.46 / 52.40 ± 2.50 |
15.58 ± 1.48 / 36.33 ± 1.08 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| norallm/normistral-7b-warm-instruct (few-shot) |
unknown |
33 |
2048 |
True |
6,194 ± 949 / 1,967 ± 619 |
3.11 |
39.83 ± 2.18 / 25.99 ± 1.56 |
47.48 ± 2.00 / 63.93 ± 1.86 |
4.55 ± 2.34 / 42.91 ± 4.05 |
49.23 ± 0.63 / 57.45 ± 0.53 |
66.17 ± 1.09 / 21.29 ± 0.90 |
10.83 ± 2.01 / 28.99 ± 1.32 |
14.66 ± 2.21 / 41.21 ± 0.84 |
2.71 ± 0.74 / 26.10 ± 0.82 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
| LumiOpen/Viking-33B (few-shot) |
33119 |
131 |
4099 |
True |
2,080 ± 700 / 331 ± 117 |
3.23 |
34.22 ± 2.47 / 22.52 ± 1.93 |
45.05 ± 2.49 / 62.23 ± 1.84 |
9.40 ± 2.63 / 44.83 ± 4.69 |
54.92 ± 1.00 / 60.33 ± 0.76 |
62.78 ± 0.97 / 15.36 ± 1.96 |
0.43 ± 1.04 / 24.15 ± 0.82 |
4.81 ± 3.43 / 36.58 ± 2.02 |
1.77 ± 0.76 / 26.00 ± 0.65 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
12.9.0 |
| norallm/normistral-7b-warm (few-shot) |
7248 |
33 |
2048 |
True |
3,175 ± 456 / 1,186 ± 354 |
3.28 |
37.80 ± 2.75 / 24.74 ± 2.30 |
40.51 ± 1.75 / 55.84 ± 2.46 |
3.35 ± 1.84 / 44.60 ± 4.67 |
49.08 ± 1.74 / 55.58 ± 1.57 |
65.81 ± 1.29 / 21.55 ± 1.19 |
-0.90 ± 1.63 / 23.10 ± 1.16 |
3.61 ± 2.89 / 35.10 ± 1.82 |
0.40 ± 1.28 / 25.12 ± 0.72 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
| 01-ai/Yi-6B (few-shot) |
6061 |
64 |
4096 |
True |
2,786 ± 532 / 784 ± 250 |
3.34 |
35.08 ± 2.24 / 25.02 ± 2.03 |
4.00 ± 2.43 / 18.67 ± 0.94 |
3.68 ± 2.25 / 35.69 ± 1.87 |
55.09 ± 0.79 / 60.88 ± 0.55 |
64.15 ± 1.03 / 18.95 ± 0.93 |
34.07 ± 2.13 / 50.17 ± 1.60 |
33.75 ± 2.28 / 54.22 ± 1.75 |
13.61 ± 1.51 / 34.38 ± 1.20 |
9.3.2 |
10.0.0 |
10.0.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| google/gemma-2b (few-shot) |
2506 |
256 |
8192 |
True |
6,087 ± 1,046 / 1,902 ± 563 |
3.36 |
19.97 ± 3.91 / 16.51 ± 3.20 |
40.21 ± 1.00 / 46.73 ± 1.82 |
2.27 ± 2.39 / 38.71 ± 4.03 |
50.55 ± 1.22 / 56.27 ± 1.09 |
63.07 ± 1.07 / 16.98 ± 0.98 |
15.04 ± 1.21 / 35.51 ± 0.80 |
30.63 ± 3.36 / 50.02 ± 2.13 |
4.90 ± 0.95 / 28.18 ± 0.88 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| LumiOpen/Viking-13B (few-shot) |
14030 |
131 |
4099 |
True |
3,480 ± 727 / 822 ± 274 |
3.37 |
28.80 ± 2.60 / 20.50 ± 2.40 |
37.20 ± 3.92 / 53.62 ± 4.07 |
2.94 ± 1.76 / 46.66 ± 3.18 |
49.57 ± 1.52 / 54.84 ± 1.68 |
63.69 ± 0.49 / 16.88 ± 1.13 |
1.17 ± 2.12 / 24.75 ± 1.44 |
11.57 ± 3.78 / 38.65 ± 1.84 |
-0.19 ± 1.08 / 25.11 ± 0.77 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
| HPLT/gpt-13b-nordic-prerelease (few-shot) |
14030 |
131 |
4099 |
True |
3,520 ± 736 / 823 ± 273 |
3.42 |
28.72 ± 2.61 / 20.53 ± 2.46 |
37.19 ± 3.92 / 53.63 ± 4.06 |
2.96 ± 1.73 / 46.67 ± 3.16 |
49.53 ± 1.49 / 54.83 ± 1.67 |
61.62 ± 1.05 / 14.33 ± 1.71 |
1.17 ± 2.28 / 24.76 ± 1.52 |
11.38 ± 3.80 / 38.52 ± 1.85 |
-0.16 ± 1.02 / 25.19 ± 0.70 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
12.6.1 |
| AI-Sweden-Models/gpt-sw3-6.7b-v2 (few-shot) |
7111 |
64 |
2048 |
True |
2,351 ± 448 / 707 ± 216 |
3.43 |
20.84 ± 2.40 / 16.93 ± 1.98 |
18.07 ± 3.41 / 27.21 ± 2.91 |
10.54 ± 2.38 / 48.37 ± 3.58 |
51.22 ± 0.94 / 57.23 ± 0.68 |
65.15 ± 1.16 / 18.96 ± 1.15 |
6.34 ± 2.61 / 28.14 ± 1.77 |
18.00 ± 3.09 / 45.08 ± 1.79 |
5.57 ± 0.93 / 28.66 ± 0.66 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.2.0 |
| AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct (few-shot) |
7111 |
64 |
2048 |
True |
2,383 ± 451 / 718 ± 221 |
3.51 |
15.35 ± 1.38 / 14.74 ± 1.30 |
2.85 ± 1.54 / 18.05 ± 0.23 |
10.99 ± 2.52 / 54.07 ± 1.93 |
50.51 ± 0.90 / 58.22 ± 0.76 |
66.38 ± 1.07 / 21.48 ± 1.21 |
30.90 ± 3.84 / 43.86 ± 4.18 |
16.81 ± 3.84 / 42.03 ± 2.42 |
11.08 ± 1.35 / 32.13 ± 1.04 |
9.2.0 |
9.2.0 |
9.2.0 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.2.0 |
| google/gemma-2b-it (few-shot) |
2506 |
256 |
8192 |
False |
6,471 ± 1,142 / 1,961 ± 584 |
3.52 |
24.44 ± 2.59 / 17.37 ± 2.03 |
34.03 ± 2.50 / 52.42 ± 2.16 |
2.25 ± 1.28 / 42.33 ± 3.11 |
42.12 ± 1.18 / 49.76 ± 1.22 |
62.41 ± 1.21 / 17.66 ± 0.54 |
15.16 ± 1.35 / 31.61 ± 1.92 |
12.67 ± 1.89 / 41.99 ± 1.17 |
2.67 ± 1.17 / 26.82 ± 0.69 |
12.5.2 |
12.1.0 |
12.1.0 |
12.4.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| mhenrichsen/danskgpt-tiny-chat (few-shot) |
1100 |
32 |
2048 |
False |
1,745 ± 978 / 686 ± 159 |
3.52 |
22.31 ± 2.55 / 19.30 ± 2.14 |
34.05 ± 2.37 / 52.43 ± 2.46 |
0.70 ± 1.11 / 40.47 ± 3.04 |
41.82 ± 2.07 / 48.91 ± 2.47 |
65.27 ± 0.25 / 17.79 ± 0.40 |
6.27 ± 1.52 / 27.63 ± 1.15 |
6.25 ± 3.25 / 37.75 ± 2.53 |
2.11 ± 1.44 / 26.00 ± 0.86 |
9.1.2 |
9.1.2 |
9.1.2 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
9.1.2 |
| AI-Sweden-Models/gpt-sw3-1.3b-instruct (few-shot) |
1445 |
64 |
2048 |
True |
4,544 ± 1,000 / 1,106 ± 359 |
3.59 |
14.73 ± 1.84 / 14.44 ± 1.74 |
27.14 ± 1.93 / 42.34 ± 2.51 |
2.65 ± 1.66 / 40.63 ± 4.02 |
46.38 ± 0.61 / 54.18 ± 0.52 |
65.48 ± 0.73 / 19.58 ± 1.08 |
0.32 ± 0.71 / 23.38 ± 0.86 |
7.00 ± 3.44 / 37.91 ± 1.85 |
0.13 ± 0.25 / 25.04 ± 0.54 |
12.5.2 |
9.3.1 |
12.1.0 |
12.4.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| AI-Sweden-Models/gpt-sw3-6.7b (few-shot) |
7111 |
64 |
2048 |
True |
2,285 ± 443 / 671 ± 205 |
3.59 |
18.23 ± 5.87 / 14.77 ± 3.36 |
22.71 ± 5.21 / 35.11 ± 6.59 |
5.03 ± 2.51 / 49.00 ± 2.64 |
49.11 ± 1.16 / 55.56 ± 1.21 |
64.58 ± 1.03 / 18.26 ± 1.00 |
1.11 ± 2.19 / 24.85 ± 1.14 |
8.76 ± 3.09 / 37.32 ± 1.76 |
1.70 ± 0.84 / 26.17 ± 0.62 |
11.0.0 |
11.0.0 |
11.0.0 |
11.0.0 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
| LumiOpen/Viking-7B (few-shot) |
7550 |
131 |
4096 |
True |
5,723 ± 1,025 / 1,670 ± 559 |
3.60 |
16.67 ± 3.76 / 14.91 ± 2.85 |
38.36 ± 2.27 / 57.74 ± 2.76 |
1.22 ± 1.77 / 37.76 ± 2.76 |
47.53 ± 1.25 / 54.08 ± 1.20 |
62.21 ± 0.78 / 14.86 ± 1.09 |
-0.28 ± 1.50 / 24.17 ± 0.86 |
1.52 ± 3.23 / 36.52 ± 1.61 |
-1.96 ± 1.11 / 23.86 ± 0.52 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
| HPLT/gpt-7b-nordic-prerelease (few-shot) |
7550 |
131 |
4096 |
True |
5,404 ± 931 / 1,638 ± 542 |
3.62 |
21.98 ± 3.33 / 18.42 ± 2.62 |
37.77 ± 3.06 / 55.35 ± 4.51 |
1.26 ± 1.86 / 34.03 ± 0.86 |
46.03 ± 1.44 / 52.54 ± 1.95 |
58.21 ± 1.54 / 11.61 ± 1.16 |
0.00 ± 0.00 / 24.00 ± 0.73 |
-0.87 ± 1.27 / 35.70 ± 1.49 |
0.00 ± 0.00 / 25.18 ± 0.77 |
12.5.2 |
12.3.2 |
12.3.2 |
12.3.2 |
12.6.1 |
12.3.2 |
12.3.2 |
12.3.2 |
| norallm/normistral-7b-scratch (few-shot) |
7248 |
33 |
2048 |
True |
3,192 ± 454 / 1,198 ± 357 |
3.66 |
14.88 ± 3.92 / 14.02 ± 2.63 |
34.66 ± 1.82 / 46.40 ± 1.53 |
0.29 ± 1.86 / 41.01 ± 2.54 |
42.16 ± 0.88 / 47.49 ± 0.98 |
63.19 ± 1.17 / 17.04 ± 1.07 |
0.58 ± 1.06 / 23.87 ± 1.16 |
4.60 ± 3.52 / 37.09 ± 1.52 |
-0.34 ± 1.37 / 24.79 ± 0.73 |
10.0.0 |
10.0.0 |
10.0.0 |
10.0.0 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| NbAiLab/nb-gpt-j-6B-alpaca (few-shot) |
6055 |
50 |
1024 |
False |
2,607 ± 592 / 680 ± 208 |
3.73 |
12.95 ± 3.80 / 11.68 ± 2.31 |
27.68 ± 3.64 / 46.61 ± 4.11 |
1.65 ± 1.96 / 47.94 ± 2.55 |
38.60 ± 0.65 / 47.40 ± 0.64 |
63.32 ± 0.32 / 16.03 ± 0.49 |
4.49 ± 1.44 / 27.32 ± 0.89 |
12.81 ± 4.57 / 37.83 ± 2.98 |
-0.68 ± 1.31 / 25.00 ± 0.79 |
9.3.1 |
10.0.1 |
10.0.1 |
12.4.0 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| Qwen/Qwen1.5-1.8B-Chat (few-shot) |
1837 |
152 |
32768 |
False |
8,304 ± 1,846 / 1,933 ± 617 |
3.73 |
18.00 ± 2.52 / 14.88 ± 1.68 |
26.58 ± 2.81 / 45.88 ± 3.40 |
0.63 ± 1.48 / 33.42 ± 0.28 |
41.66 ± 1.48 / 49.40 ± 1.53 |
57.19 ± 1.18 / 11.87 ± 0.68 |
22.17 ± 1.31 / 39.97 ± 1.18 |
12.85 ± 3.11 / 42.13 ± 2.09 |
7.01 ± 0.62 / 30.16 ± 0.46 |
12.5.2 |
11.0.0 |
12.1.0 |
12.5.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| AI-Sweden-Models/gpt-sw3-1.3b (few-shot) |
1445 |
64 |
2048 |
True |
4,608 ± 988 / 1,115 ± 354 |
3.75 |
8.80 ± 5.54 / 8.63 ± 4.48 |
28.65 ± 2.81 / 47.83 ± 3.55 |
2.84 ± 1.81 / 49.21 ± 1.95 |
45.34 ± 0.88 / 51.59 ± 0.80 |
62.17 ± 1.12 / 14.96 ± 1.16 |
-1.31 ± 1.31 / 24.58 ± 0.99 |
3.02 ± 3.77 / 36.58 ± 2.16 |
-0.33 ± 1.17 / 24.65 ± 0.48 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| AI-Sweden-Models/gpt-sw3-356m-instruct (few-shot) |
471 |
64 |
2048 |
True |
5,855 ± 1,373 / 1,223 ± 391 |
3.76 |
11.28 ± 0.96 / 11.02 ± 0.85 |
34.94 ± 3.80 / 49.66 ± 3.96 |
2.08 ± 1.48 / 45.41 ± 3.83 |
36.59 ± 1.41 / 42.03 ± 1.44 |
63.38 ± 0.84 / 15.95 ± 1.16 |
-0.09 ± 1.02 / 23.32 ± 0.76 |
-0.76 ± 3.27 / 35.04 ± 1.77 |
0.28 ± 0.39 / 25.19 ± 0.77 |
12.5.2 |
9.3.2 |
12.1.0 |
12.4.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| Qwen/Qwen1.5-1.8B (few-shot) |
1837 |
152 |
32768 |
True |
5,666 ± 1,328 / 1,256 ± 408 |
3.77 |
9.83 ± 3.50 / 8.97 ± 2.64 |
29.03 ± 2.48 / 46.75 ± 3.69 |
0.56 ± 0.87 / 33.34 ± 0.23 |
46.43 ± 0.74 / 53.20 ± 0.47 |
56.43 ± 1.74 / 11.67 ± 1.17 |
14.86 ± 1.85 / 33.52 ± 1.63 |
17.56 ± 2.63 / 45.31 ± 1.78 |
4.78 ± 1.48 / 27.73 ± 1.32 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| mhenrichsen/danskgpt-tiny (few-shot) |
1100 |
32 |
2048 |
True |
8,597 ± 1,983 / 1,926 ± 600 |
3.84 |
14.13 ± 3.50 / 12.15 ± 3.14 |
26.31 ± 5.33 / 44.07 ± 6.36 |
-0.54 ± 1.46 / 44.56 ± 3.34 |
32.12 ± 1.62 / 38.99 ± 1.42 |
62.61 ± 0.99 / 15.12 ± 0.59 |
-2.76 ± 1.71 / 22.41 ± 1.17 |
5.08 ± 2.61 / 35.14 ± 1.72 |
-0.70 ± 0.94 / 24.83 ± 0.59 |
0.0.0 |
0.0.0 |
0.0.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
0.0.0 |
| AI-Sweden-Models/gpt-sw3-356m (few-shot) |
471 |
64 |
2048 |
True |
5,758 ± 1,348 / 1,215 ± 391 |
3.85 |
16.13 ± 4.02 / 14.90 ± 3.13 |
27.61 ± 2.14 / 39.77 ± 1.85 |
1.96 ± 2.25 / 38.40 ± 2.99 |
34.79 ± 1.52 / 39.67 ± 1.69 |
59.05 ± 1.42 / 12.41 ± 1.13 |
1.00 ± 1.72 / 23.91 ± 0.88 |
4.85 ± 3.16 / 36.78 ± 1.41 |
0.28 ± 0.38 / 25.19 ± 0.78 |
9.3.1 |
9.3.1 |
9.3.2 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.2 |
| allenai/OLMo-7B (few-shot) |
6888 |
50 |
2051 |
True |
5,403 ± 1,133 / 1,294 ± 423 |
3.86 |
26.76 ± 3.11 / 19.46 ± 2.38 |
30.76 ± 4.38 / 44.83 ± 4.36 |
0.55 ± 1.73 / 39.40 ± 4.57 |
45.65 ± 1.22 / 52.49 ± 1.01 |
50.86 ± 0.68 / 9.46 ± 0.54 |
0.26 ± 1.33 / 23.32 ± 0.83 |
6.94 ± 1.82 / 37.66 ± 1.18 |
-0.11 ± 0.71 / 24.99 ± 0.40 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
| Qwen/Qwen1.5-0.5B-Chat (few-shot) |
620 |
152 |
32768 |
False |
11,740 ± 3,000 / 2,209 ± 721 |
4.02 |
17.38 ± 2.04 / 15.74 ± 1.99 |
10.72 ± 3.35 / 25.21 ± 3.80 |
1.32 ± 1.08 / 42.05 ± 3.69 |
34.58 ± 0.97 / 40.37 ± 1.02 |
55.87 ± 5.22 / 11.87 ± 1.03 |
4.56 ± 1.88 / 25.87 ± 1.72 |
22.41 ± 3.16 / 42.73 ± 0.96 |
1.71 ± 0.99 / 25.84 ± 0.79 |
12.5.2 |
11.0.0 |
12.1.0 |
12.4.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| allenai/OLMo-7B-Twin-2T (few-shot) |
6888 |
50 |
2051 |
True |
5,484 ± 1,125 / 1,317 ± 425 |
4.02 |
7.52 ± 3.92 / 6.60 ± 2.84 |
18.30 ± 3.89 / 27.62 ± 5.78 |
3.23 ± 1.94 / 45.74 ± 3.06 |
46.35 ± 1.42 / 51.37 ± 1.43 |
53.01 ± 1.10 / 10.72 ± 0.80 |
2.17 ± 1.53 / 23.73 ± 0.99 |
0.22 ± 2.74 / 35.08 ± 1.48 |
-0.65 ± 1.58 / 24.75 ± 1.03 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
| Qwen/Qwen1.5-0.5B (few-shot) |
620 |
152 |
32768 |
True |
11,371 ± 2,924 / 2,122 ± 692 |
4.06 |
19.01 ± 1.91 / 17.08 ± 1.83 |
8.88 ± 1.86 / 24.27 ± 2.45 |
0.66 ± 1.41 / 37.98 ± 4.14 |
32.78 ± 2.33 / 38.31 ± 2.81 |
55.57 ± 1.04 / 8.04 ± 0.82 |
7.21 ± 1.78 / 29.73 ± 1.08 |
16.56 ± 3.13 / 42.30 ± 1.26 |
0.62 ± 1.30 / 25.65 ± 0.72 |
12.5.2 |
10.0.1 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| AI-Sweden-Models/gpt-sw3-126m-instruct (few-shot) |
186 |
64 |
2048 |
True |
7,717 ± 1,553 / 2,013 ± 625 |
4.21 |
13.98 ± 1.54 / 13.46 ± 1.42 |
6.37 ± 3.38 / 25.43 ± 4.09 |
0.41 ± 0.80 / 33.31 ± 0.24 |
20.46 ± 2.90 / 24.27 ± 3.23 |
60.87 ± 0.92 / 12.82 ± 1.14 |
0.53 ± 1.10 / 24.39 ± 0.85 |
4.72 ± 3.89 / 35.76 ± 1.86 |
-0.07 ± 0.75 / 24.90 ± 0.90 |
11.0.0 |
9.3.2 |
11.0.0 |
12.4.0 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
| RuterNorway/Llama-2-7b-chat-norwegian (few-shot) |
unknown |
32 |
4096 |
False |
10,890 ± 2,686 / 2,186 ± 750 |
4.23 |
10.12 ± 1.24 / 9.84 ± 1.12 |
10.65 ± 3.65 / 28.33 ± 5.27 |
-0.66 ± 1.24 / 33.61 ± 0.26 |
26.08 ± 3.96 / 28.87 ± 4.21 |
56.92 ± 0.98 / 8.57 ± 0.76 |
0.10 ± 1.50 / 26.50 ± 1.00 |
4.29 ± 5.87 / 35.00 ± 1.75 |
-0.88 ± 1.17 / 24.43 ± 0.74 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.2 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| allenai/OLMo-1B (few-shot) |
1177 |
50 |
2051 |
True |
8,536 ± 1,926 / 1,940 ± 619 |
4.32 |
13.39 ± 2.60 / 12.39 ± 2.46 |
17.94 ± 5.58 / 32.80 ± 3.63 |
-2.02 ± 2.28 / 40.63 ± 4.12 |
23.65 ± 2.96 / 26.24 ± 3.20 |
48.87 ± 1.42 / 5.39 ± 0.62 |
-0.33 ± 0.61 / 23.91 ± 0.71 |
0.05 ± 2.96 / 34.67 ± 1.78 |
-0.08 ± 0.81 / 25.21 ± 0.56 |
12.5.2 |
12.1.0 |
12.1.0 |
12.1.0 |
12.6.1 |
12.1.0 |
12.1.0 |
12.1.0 |
| NbAiLab/nb-gpt-j-6B-v2 (few-shot) |
6051 |
50 |
1024 |
False |
2,556 ± 580 / 681 ± 214 |
4.41 |
0.24 ± 0.25 / 0.25 ± 0.21 |
27.80 ± 6.39 / 43.80 ± 5.16 |
0.56 ± 0.51 / 34.04 ± 1.28 |
6.84 ± 6.83 / 21.33 ± 6.27 |
53.76 ± 0.47 / 11.17 ± 0.49 |
-1.83 ± 1.68 / 23.94 ± 1.25 |
0.99 ± 3.76 / 34.10 ± 2.62 |
-0.48 ± 0.94 / 24.73 ± 0.61 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
| AI-Sweden-Models/gpt-sw3-126m (few-shot) |
186 |
64 |
2048 |
True |
8,958 ± 1,815 / 2,240 ± 696 |
4.43 |
3.43 ± 2.66 / 5.56 ± 1.90 |
9.18 ± 4.25 / 26.36 ± 3.94 |
-0.22 ± 1.53 / 34.20 ± 0.84 |
16.64 ± 3.32 / 19.46 ± 3.63 |
52.34 ± 1.60 / 8.84 ± 0.78 |
-0.58 ± 0.97 / 24.00 ± 0.77 |
5.18 ± 4.75 / 36.68 ± 2.20 |
-1.28 ± 0.99 / 24.75 ± 0.93 |
9.2.0 |
9.2.0 |
9.2.0 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.2.0 |
| RJuro/kanelsnegl-v0.1 (few-shot) |
7242 |
32 |
512 |
True |
9,757 ± 2,047 / 2,200 ± 705 |
4.47 |
0.00 ± 0.00 / 0.00 ± 0.00 |
13.00 ± 4.17 / 24.41 ± 3.12 |
0.00 ± 0.00 / 33.25 ± 0.23 |
0.00 ± 0.00 / 12.39 ± 1.52 |
61.25 ± 0.17 / 12.03 ± 0.21 |
0.00 ± 0.00 / 24.00 ± 0.73 |
0.00 ± 0.00 / 35.86 ± 1.26 |
0.04 ± 0.14 / 25.18 ± 0.77 |
9.3.1 |
9.3.1 |
9.3.1 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
9.3.1 |
| RJuro/kanelsnegl-v0.2 (few-shot) |
7242 |
32 |
512 |
True |
1,373 ± 120 / 709 ± 172 |
4.53 |
0.00 ± 0.00 / 0.00 ± 0.00 |
4.81 ± 2.69 / 19.31 ± 1.01 |
0.00 ± 0.00 / 33.25 ± 0.23 |
0.00 ± 0.00 / 30.05 ± 4.99 |
61.06 ± 0.14 / 12.02 ± 0.15 |
0.00 ± 0.00 / 24.00 ± 0.73 |
0.00 ± 0.00 / 35.86 ± 1.26 |
0.15 ± 0.64 / 25.21 ± 0.79 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
11.0.0 |
| NbAiLab/nb-gpt-j-6B@sharded (few-shot) |
unknown |
50 |
1024 |
True |
2,630 ± 605 / 684 ± 217 |
4.59 |
0.36 ± 0.40 / 1.82 ± 1.16 |
11.00 ± 7.09 / 26.09 ± 6.96 |
-0.11 ± 1.16 / 33.76 ± 0.86 |
5.15 ± 6.60 / 17.35 ± 5.86 |
51.83 ± 0.77 / 10.14 ± 0.49 |
-0.96 ± 1.47 / 23.86 ± 1.33 |
3.51 ± 3.46 / 35.41 ± 2.22 |
0.73 ± 1.39 / 25.54 ± 1.00 |
9.3.1 |
10.0.1 |
10.0.1 |
12.5.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| NorGLM/NorGPT-369M (few-shot) |
unknown |
64 |
1024 |
True |
19,896 ± 5,099 / 3,848 ± 1,251 |
4.66 |
1.13 ± 1.19 / 0.97 ± 1.03 |
2.06 ± 2.30 / 20.38 ± 2.71 |
-0.36 ± 0.97 / 41.52 ± 4.00 |
0.32 ± 0.12 / 4.20 ± 0.61 |
54.00 ± 0.80 / 9.08 ± 0.87 |
-2.57 ± 2.04 / 23.19 ± 1.37 |
3.26 ± 1.64 / 29.55 ± 2.52 |
-0.62 ± 0.87 / 24.55 ± 0.66 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
12.5.2 |
| peter-sk/gpt-neox-da (few-shot) |
1515 |
50 |
1024 |
True |
6,025 ± 1,442 / 1,342 ± 431 |
4.77 |
0.64 ± 0.89 / 0.52 ± 0.69 |
-0.52 ± 1.72 / 28.55 ± 1.60 |
-0.02 ± 1.55 / 36.82 ± 2.52 |
0.48 ± 0.27 / 2.89 ± 0.53 |
50.23 ± 0.89 / 6.09 ± 0.27 |
0.90 ± 0.92 / 26.20 ± 1.02 |
4.10 ± 2.68 / 33.71 ± 1.88 |
0.04 ± 1.16 / 25.21 ± 0.48 |
10.0.1 |
10.0.1 |
10.0.1 |
10.0.1 |
12.6.1 |
10.0.1 |
10.0.1 |
10.0.1 |
| ai-forever/mGPT (few-shot) |
unknown |
100 |
1024 |
True |
13,551 ± 4,259 / 2,563 ± 838 |
5.05 |
0.65 ± 0.68 / 0.59 ± 0.63 |
2.61 ± 2.75 / 20.51 ± 2.48 |
-0.73 ± 1.72 / 41.15 ± 3.71 |
1.99 ± 1.69 / 2.68 ± 1.87 |
35.64 ± 4.11 / 4.70 ± 2.01 |
-0.61 ± 0.54 / 24.71 ± 1.18 |
6.94 ± 3.67 / 38.18 ± 1.72 |
-1.12 ± 0.87 / 24.71 ± 0.88 |
9.3.1 |
10.0.1 |
11.0.0 |
12.5.1 |
12.6.1 |
11.0.0 |
11.0.0 |
11.0.0 |
| Sigurdur/icebreaker (few-shot) |
110 |
32 |
1024 |
False |
48,619 ± 7,681 / 13,831 ± 4,404 |
5.17 |
0.00 ± 0.00 / 0.00 ± 0.00 |
0.00 ± 0.00 / 18.12 ± 0.19 |
0.00 ± 0.00 / 33.25 ± 0.23 |
0.00 ± 0.00 / 0.04 ± 0.01 |
37.85 ± 0.55 / 0.76 ± 0.08 |
0.26 ± 0.46 / 23.72 ± 0.47 |
-0.75 ± 1.90 / 34.96 ± 1.13 |
-0.88 ± 0.48 / 24.60 ± 0.50 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |
12.7.0 |